Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c66fb17947106fdeeb264d1b58d30291d15892f6746189389fb554d229738f
+oid sha256:99589c39c671d0e2591c29d1e06011399295330363dc12e50bad667dcc1e2746
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0707852b6cf9996138de510986c7e892537fb6029ff81888afcf7f5b07c25b26
+oid sha256:cf85a12cbfc7f1ab1df2b8d14c926ea9325cf967123feb75f41357d9213feaa0
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2ff9630f3c5130a9863c241cdc11ae5b7cc657990dab03b6808984c6718c2e
+oid sha256:a463d5feac318c09783e529b68d2719872f249d90beddb2b474a4acc955e8e79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
+oid sha256:59fb9c579d7f7f4aa986f5f762cd9981f0dcd26b5aa72ad6a0ef96ae89405fbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00971884762235335,
+  "epoch": 0.012727062362605577,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 18.487,
       "eval_steps_per_second": 9.244,
       "step": 42
+    },
+    {
+      "epoch": 0.011570056693277797,
+      "grad_norm": 0.6662918329238892,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.1166,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4519079347945472e+16,
+  "total_flos": 1.872683801247744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null